Deep Learning Transcends the Bag of Words

           Tweet Previous post Tags: Beer, Deep Learning, Generative Models, Recurrent Neural Networks, Zachary Lipton Generative RNNs are now widely popular, many modeling text at the character level. While character-level modeling is enticing on account of its generality and computational advantages, such RNNs typically generate text in an unsupervised fashion. This post shows how to generate contextually relevant character-level text and explains a couple recent papers that perform the task successfully. comments By Zachary Chase Lipton Deep learning has risen to prominence, both delighting and enraging computer scientists, following a number of breakthrough results on difficult classification tasks. Convolutional neural networks demonstrate an unprecedented ability to recognize objects in images. A variety of neural networks have similarly revolutionized the field of speech recognition. In machine learning parlance, these…


Link to Full Article: Deep Learning Transcends the Bag of Words